IdePHICS @ NeurIPS 2021

© 2021 EPFL

© 2021 EPFL

Four IdePHICS papers have been accepted to thirty-five conference on Neural Information Processing Systems (NeurIPS), putting the lab among the top academic contributors to the conference. Due to Covid-19, this year NeurIPS edition will be a virtual-only conference held from Monday, December 6th through Tuesday, December 124h, 2021. A mirror conference is co-organised by IdePHICS on dec. 6 in EPFL. 

The accepted IdePHICS papers are as follows:

Learning Gaussian Mixtures with Generalized Linear Models: Precise Asymptotics in High-dimensions, Bruno Loureiro · Gabriele Sicuro · Cedric Gerbelot · Alessandro Pacco · Florent Krzakala · Lenka Zdeborová (spotlight paper)

Learning curves of generic features maps for realistic datasets with a teacher-student model,Bruno Loureiro · Cedric Gerbelot · Hugo Cui · Sebastian Goldt · Florent Krzakala · Marc Mezard · Lenka Zdeborová

Generalization Error Rates in Kernel Regression: The Crossover from the Noiseless to Noisy Regim, Hugo Cui · Bruno Loureiro · Florent Krzakala · Lenka Zdeborová

Photonic Differential Privacy with Direct Feedback Alignment,Ruben Ohana · Hamlet Medina · Julien Launay · Alessandro Cappelli · Iacopo Poli · Liva Ralaivola · Alain Rakotomamonjy